Bike Peddler

library(ggplot2)

source("process_data.R")
base_columns <- names(store)[!names(store) %in% c("Year", "Month")]

GGally::ggpairs(store, columns = base_columns)

 plot: [1,1] [==-------------------------------------------------------]  4% est: 0s 
 plot: [1,2] [=====----------------------------------------------------]  8% est: 6s 
 plot: [1,3] [=======--------------------------------------------------] 12% est: 5s 
 plot: [1,4] [=========------------------------------------------------] 16% est: 4s 
 plot: [1,5] [===========----------------------------------------------] 20% est: 3s 
 plot: [2,1] [==============-------------------------------------------] 24% est: 3s 
 plot: [2,2] [================-----------------------------------------] 28% est: 3s 
 plot: [2,3] [==================---------------------------------------] 32% est: 2s 
 plot: [2,4] [=====================------------------------------------] 36% est: 2s 
 plot: [2,5] [=======================----------------------------------] 40% est: 2s 
 plot: [3,1] [=========================--------------------------------] 44% est: 2s 
 plot: [3,2] [===========================------------------------------] 48% est: 2s 
 plot: [3,3] [==============================---------------------------] 52% est: 1s 
 plot: [3,4] [================================-------------------------] 56% est: 1s 
 plot: [3,5] [==================================-----------------------] 60% est: 1s 
 plot: [4,1] [====================================---------------------] 64% est: 1s 
 plot: [4,2] [=======================================------------------] 68% est: 1s 
 plot: [4,3] [=========================================----------------] 72% est: 1s 
 plot: [4,4] [===========================================--------------] 76% est: 1s 
 plot: [4,5] [==============================================-----------] 80% est: 0s 
 plot: [5,1] [================================================---------] 84% est: 0s 
 plot: [5,2] [==================================================-------] 88% est: 0s 
 plot: [5,3] [====================================================-----] 92% est: 0s 
 plot: [5,4] [=======================================================--] 96% est: 0s 
 plot: [5,5] [=========================================================]100% est: 0s 
                                                                                     

GGally::ggpairs(store, columns = c(base_columns, "Year"),
                mapping = ggplot2::aes(color = Year))

 plot: [1,1] [==-------------------------------------------------------]  3% est: 0s 
 plot: [1,2] [===------------------------------------------------------]  6% est: 2s 
 plot: [1,3] [=====----------------------------------------------------]  8% est: 3s 
 plot: [1,4] [======---------------------------------------------------] 11% est: 3s 
 plot: [1,5] [========-------------------------------------------------] 14% est: 2s 
 plot: [1,6] [==========-----------------------------------------------] 17% est: 2s 
 plot: [2,1] [===========----------------------------------------------] 19% est: 4s 
 plot: [2,2] [=============--------------------------------------------] 22% est: 4s 
 plot: [2,3] [==============-------------------------------------------] 25% est: 3s 
 plot: [2,4] [================-----------------------------------------] 28% est: 3s 
 plot: [2,5] [=================----------------------------------------] 31% est: 3s 
 plot: [2,6] [===================--------------------------------------] 33% est: 3s 
 plot: [3,1] [=====================------------------------------------] 36% est: 3s 
 plot: [3,2] [======================-----------------------------------] 39% est: 3s 
 plot: [3,3] [========================---------------------------------] 42% est: 2s 
 plot: [3,4] [=========================--------------------------------] 44% est: 2s 
 plot: [3,5] [===========================------------------------------] 47% est: 2s 
 plot: [3,6] [============================-----------------------------] 50% est: 2s 
 plot: [4,1] [==============================---------------------------] 53% est: 2s 
 plot: [4,2] [================================-------------------------] 56% est: 2s 
 plot: [4,3] [=================================------------------------] 58% est: 2s 
 plot: [4,4] [===================================----------------------] 61% est: 2s 
 plot: [4,5] [====================================---------------------] 64% est: 1s 
 plot: [4,6] [======================================-------------------] 67% est: 1s 
 plot: [5,1] [========================================-----------------] 69% est: 1s 
 plot: [5,2] [=========================================----------------] 72% est: 1s 
 plot: [5,3] [===========================================--------------] 75% est: 1s 
 plot: [5,4] [============================================-------------] 78% est: 1s 
 plot: [5,5] [==============================================-----------] 81% est: 1s 
 plot: [5,6] [================================================---------] 83% est: 1s 
 plot: [6,1] [=================================================--------] 86% est: 1s 
 plot: [6,2] [===================================================------] 89% est: 0s 
 plot: [6,3] [====================================================-----] 92% est: 0s 
 plot: [6,4] [======================================================---] 94% est: 0s 
 plot: [6,5] [=======================================================--] 97% est: 0s 
 plot: [6,6] [=========================================================]100% est: 0s 
                                                                                     

GGally::ggpairs(category, columns = base_columns,
                mapping = ggplot2::aes(color = Category))

 plot: [1,1] [==-------------------------------------------------------]  4% est: 0s 
 plot: [1,2] [=====----------------------------------------------------]  8% est: 1s 
 plot: [1,3] [=======--------------------------------------------------] 12% est: 2s 
 plot: [1,4] [=========------------------------------------------------] 16% est: 2s 
 plot: [1,5] [===========----------------------------------------------] 20% est: 2s 
 plot: [2,1] [==============-------------------------------------------] 24% est: 2s 
 plot: [2,2] [================-----------------------------------------] 28% est: 2s 
 plot: [2,3] [==================---------------------------------------] 32% est: 2s 
 plot: [2,4] [=====================------------------------------------] 36% est: 2s 
 plot: [2,5] [=======================----------------------------------] 40% est: 1s 
 plot: [3,1] [=========================--------------------------------] 44% est: 1s 
 plot: [3,2] [===========================------------------------------] 48% est: 1s 
 plot: [3,3] [==============================---------------------------] 52% est: 1s 
 plot: [3,4] [================================-------------------------] 56% est: 1s 
 plot: [3,5] [==================================-----------------------] 60% est: 1s 
 plot: [4,1] [====================================---------------------] 64% est: 1s 
 plot: [4,2] [=======================================------------------] 68% est: 1s 
 plot: [4,3] [=========================================----------------] 72% est: 1s 
 plot: [4,4] [===========================================--------------] 76% est: 1s 
 plot: [4,5] [==============================================-----------] 80% est: 0s 
 plot: [5,1] [================================================---------] 84% est: 0s 
 plot: [5,2] [==================================================-------] 88% est: 0s 
 plot: [5,3] [====================================================-----] 92% est: 0s 
 plot: [5,4] [=======================================================--] 96% est: 0s 
 plot: [5,5] [=========================================================]100% est: 0s 
                                                                                     

p <- GGally::ggpairs(type, columns = base_columns,
                     mapping = ggplot2::aes(color = Type)) 
plotly::ggplotly(p)

lm_fit <- lm(Revenue ~ Category + Type + Qty_Sold, data = type)
summary(lm_fit)

Call:
lm(formula = Revenue ~ Category + Type + Qty_Sold, data = type)

Residuals:
    Min      1Q  Median      3Q     Max 
-9908.3  -829.8  -113.4   669.7  9003.4 

Coefficients: (1 not defined because of singularities)
              Estimate Std. Error t value Pr(>|t|)    
(Intercept)   -2415.49    1016.48  -2.376 0.019095 *  
CategoryBikes 15021.33    1057.10  14.210  < 2e-16 ***
TypeHelmets   -1374.45     944.01  -1.456 0.148056    
TypeHybrid    -2954.91     864.20  -3.419 0.000863 ***
TypeKids      -9991.63     855.47 -11.680  < 2e-16 ***
TypeMountain  -2076.47     852.78  -2.435 0.016391 *  
TypeParts     -9437.96    2844.83  -3.318 0.001208 ** 
TypeRoad            NA         NA      NA       NA    
Qty_Sold        106.17      16.83   6.307 5.14e-09 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 2558 on 118 degrees of freedom
Multiple R-squared:  0.7644,    Adjusted R-squared:  0.7505 
F-statistic: 54.71 on 7 and 118 DF,  p-value: < 2.2e-16

type %>%
  dplyr::group_by(Category, Type) %>%
  dplyr::summarize(min = min(Qty_Sold), median = median(Qty_Sold), 
                   max = max(Qty_Sold))

boot_type <- type %>%
  dplyr::select(Category, Type, Qty_Sold) %>%
  sample_n(10000, replace = TRUE)
boot_type$Revenue <- predict(lm_fit, boot_type)

input_data_frame <- read.table(header = TRUE, stringsAsFactors = FALSE, text = '
Category Type input
Acessories  Clothes 60
Acessories  Helmets 70
Acessories  Parts 200
Bikes   Hybrid 20
Bikes   Kids 11
Bikes   Mountain 10 
Bikes   Road 11
')
get_revenue_prediction <- function(dat, input_data_frame) {
  # dat <- boot_type
  
  percentiles <- dat %>%
    dplyr::group_by(Category, Type) %>%
    dplyr::mutate(percentile = ntile(Qty_Sold, 10)) %>%
    dplyr::group_by(Category, Type, percentile) %>%
    dplyr::mutate(min = min(Qty_Sold), max = max(Qty_Sold)) %>%
    dplyr::left_join(input_data_frame, c("Category", "Type")) %>%
    dplyr::filter(max >= input & min < input)
  percentiles
}

pred <- get_revenue_prediction(boot_type, input_data_frame) %>%
  dplyr::select(Category, Type, Revenue) %>%
  dplyr::mutate(Data = "Selected")
plot_data <- boot_type %>%
  dplyr::select(Category, Type, Revenue) %>%
  dplyr::mutate(Data = "All")
plot_data <- rbind(pred, plot_data)
p <- ggplot(plot_data, aes(Data, Revenue)) + geom_point(stat = "median")

Error: Found object is not a stat.